Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning
Jun Shu, Xiang Yuan, Deyu Meng, Zongben Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add DAC-MR | MAML · miniImageNet 5-way 1-shot | accuracy: 46.75 -> 47.48 | Improved |
| add DAC-MR | ProtoNet ResNet-12 · miniImageNet 5-way 1-shot | accuracy: 55.59 -> 57.15 | Improved |
| add DAC-MR | R2D2 (96-192-384-512) · miniImageNet 5-way 5-shot | accuracy: 73.17 -> 73.18 | No clear effect |
| add DAC-MR | R2D2 ResNet-12 · miniImageNet 5-way 1-shot | accuracy: 58.80 -> 61.31 | Improved |
| add DAC-MR | MetaOptNet-SVM · CIFAR-FS 5-way 1-shot | accuracy: 71.22 -> 74.16 | Improved |
| add DAC-MR | TSA · Meta-Dataset unseen domains average | accuracy: 78.1 -> 80.4 | Improved |
| add DAC-MR | TSA · Meta-Dataset Quick Draw | accuracy: 81.7 -> 81.7 | No clear effect |
| add DAC-MR | TSA · Meta-Dataset Fungi | accuracy: 66.3 -> 67.2 | Improved |
| add DAC-MR | iLPC · miniImageNet 1-shot (semi-supervised) | accuracy: 82.75 -> 85.93 | Improved |
| add DAC-MR with gamma=1 on top of feature-adaptation-only | CST · Office-Home average | accuracy: 73.0 -> 73.7 | Improved |
| add DAC-MR | ARM-BN · Tiny ImageNet-C worst case | accuracy: 28.6 -> 28.3 | Hurt |
| add DAC-MR | ARM-LL · Tiny ImageNet-C worst case | accuracy: 21.2 -> 21.2 | No clear effect |
Closest papers by meaning
- Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level (CVPR 2023 · similarity 0.88)
- Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models (ICML 2024 · similarity 0.88)
- Meta-Learning Requires Meta-Augmentation (NeurIPS 2020 · similarity 0.88)
- Towards Automated Knowledge Integration From Human-Interpretable Representations (ICLR 2025 · similarity 0.86)
- Learning to Learn with Contrastive Meta-Objective (NeurIPS 2025 · similarity 0.86)
- Provable Meta-Learning with Low-Rank Adaptations (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
